Preprint
Aug 2026
Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance
This work proposes a new approach to working with imperfect tracking predictions through an interactive prediction correction workflow taking place as a conversation with a multimodal large language model, which is tailor to a sonar fish tracking dataset as an initial proof of concept.
Kai Van Brunt, Justin Kay, Sara Beery
· 0 citations